Triple

T16168469
Position Surface form Disambiguated ID Type / Status
Subject Lewis family E392369 entity
Predicate associatedWith P37 FINISHED
Object Lewis Oil E1198297 NE FINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Lewis Oil | Statement: [Lewis family, associatedWith, Lewis Oil]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lewis Oil
Context triple: [Lewis family, associatedWith, Lewis Oil]
  • A. Lewis Oil chosen
    Lewis Oil is a petroleum-related business enterprise associated with entrepreneur Josh Lewis.
  • B. Union Oil
    Union Oil was a major American petroleum company, historically significant as a prominent West Coast oil producer and refiner later absorbed into Chevron.
  • C. Belridge Oil Company
    Belridge Oil Company was a major California-based petroleum firm known for developing and operating significant oil fields before being acquired by Shell Oil in the late 20th century.
  • D. Petrox Oil
    Petrox Oil is a fictional multinational petroleum corporation featured as the sponsoring company behind the expedition in the 1976 film "King Kong."
  • E. Hancock Oil Company
    Hancock Oil Company was a prominent early 20th-century American petroleum company founded and developed by businessman and philanthropist G. Allan Hancock.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d87f1d32208190942e4e499a80c18c completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e21eb4ea9c81908806f9771ae80148 completed April 17, 2026, 11:51 a.m.
NED1 Entity disambiguation (via context triple) batch_69fffefc3e088190975ecbdaeba7ee84 completed May 10, 2026, 3:43 a.m.
Created at: April 10, 2026, 5:02 a.m.